To Solve Bilevel Optimization with Nonconvex Lower Levels, We Need Second-Order Stationarity
cs.LG
Submitted: 2026-09-24
Updated: 2026-09-24
Terminology
Sources
- Amortized Implicit Differentiation for Stochastic Bilevel Optimization
- How Smooth Is Attention?
- Approximation Methods for Bilevel Programming
- A Correspondence-Driven Approach for Bilevel Decision-making with Nonconvex Lower-Level Problems
- A Discretization Approach for Bilevel Optimization with Low-Dimensional and Non-Convex Lower-Level
- Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning
- On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation
- Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-loop and Hessian-free Solution Strategy
- SUN-DSBO: A Structured Unified Framework for Nonconvex Decentralized Stochastic Bilevel Optimization
- SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
- A Generalized Alternating Method for Bilevel Learning under the Polyak-{\L}ojasiewicz Condition
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks